Wavelets on Graphs via Deep Learning

By Raif M. Rustamov, Leonidas J. Guibas. 2013

84 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistical and Nonlinear Physics

In Graph Learning

Citations in the corpus

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering (2016, methodology): “On the other hand, we will also improve this framework with tools developed in GSP, including graph wavelet operators [14, 9, 11, 6, 30], spectral graph coarsening techniques [33], and improved localization properties [36, 26, 27].”
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, methodology): “[47]. Spectral analysis techniques were extended to graphs considering the orthogonal eigenfunctions of the Laplacian operator as a generalization of the Fourier basis. Constructions such as wavelets [14, 18, 21, 39, 45] or algorithms such as dictionary learning [62], Lasso [9], PCA [43, 44], or mat”
Geometric Deep Learning: Going beyond Euclidean data (2016, neutral): “In [87], the authors developed an unsupervised”
Deep Haar Scattering Networks (2015, background): “Haar wavelets can easily be constructed on graphs [7, 26].”
Unsupervised Deep Haar Scattering on Graphs (2014, background): “Haar wavelet transforms are flexible representations which characterize multiscale signal patterns on graphs [6, 10, 11].”
Learning the Structural Vocabulary of a Network (2017, methodology): “Wavelets have been used to compress signals coming from an underlying graphical structure by using the lifting scheme to sparsely represent an entire class of signals (Rustamov & Guibas, 2013).”
Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifolds (2018, background): “This is an essential barrier to adopt CNN to conduct learning on manifolds and graphs except for a few recent work where convolution is deﬁned in the frequency space of the LB operator [5, 31, 27, 28].”
Learning Structural Node Embeddings via Diffusion Wavelets (2017, background): “Another line of related work are graph diffusion kernels [5] which have been utilized for various graph modeling purposes [3, 22, 29, 34].”
Relational Graph Attention Networks (2018, background): “Hybrid approaches combine spectral and spatial approaches, trading their advantages and deﬁciencies against each-other (Bronstein et al., 2017; Rustamov and Guibas, 2013; Szlam et al., 2005; Gavish et al., 2010).”